Multistep Prediction of Vehicle States using Transformers

This thesis focussed on developing transformer models for multistep prediction of vehicle states.

Completed Bachelor Thesis

We develop transformer models for multistep prediction of vehicle states. Multistep prediction is the prediction of states based on initial states and a series of control inputs. We test different modifications of the transformer architecture using the example of the prediction of a ship simulation. Research in NLP promises advantages w.r.t. training time and prediction accuracy for the transformer architecture compared to a state-of-the-art LSTM model. We
also investigate whether positional encodings are useful in this scenario and if a transformer model can learn the order of the inputs without positional encodings.

Supervisors

To the top of the page